Book Image

Deep Reinforcement Learning with Python - Second Edition

By : Sudharsan Ravichandiran
Book Image

Deep Reinforcement Learning with Python - Second Edition

By: Sudharsan Ravichandiran

Overview of this book

With significant enhancements in the quality and quantity of algorithms in recent years, this second edition of Hands-On Reinforcement Learning with Python has been revamped into an example-rich guide to learning state-of-the-art reinforcement learning (RL) and deep RL algorithms with TensorFlow 2 and the OpenAI Gym toolkit. In addition to exploring RL basics and foundational concepts such as Bellman equation, Markov decision processes, and dynamic programming algorithms, this second edition dives deep into the full spectrum of value-based, policy-based, and actor-critic RL methods. It explores state-of-the-art algorithms such as DQN, TRPO, PPO and ACKTR, DDPG, TD3, and SAC in depth, demystifying the underlying math and demonstrating implementations through simple code examples. The book has several new chapters dedicated to new RL techniques, including distributional RL, imitation learning, inverse RL, and meta RL. You will learn to leverage stable baselines, an improvement of OpenAI’s baseline library, to effortlessly implement popular RL algorithms. The book concludes with an overview of promising approaches such as meta-learning and imagination augmented agents in research. By the end, you will become skilled in effectively employing RL and deep RL in your real-world projects.
Table of Contents (22 chapters)
Other Books You May Enjoy

Finding the best advertisement banner using bandits

In this section, let's see how to find the best advertisement banner using bandits. Suppose we are running a website and we have five different banners for a single advertisement on our website, and say we want to figure out which advertisement banner is most liked by the users.

We can frame this problem as a MAB problem. The five advertisement banners represent the five arms of the bandit, and we assign +1 reward if the user clicks the advertisement and 0 reward if the user does not click the advertisement. So, to find out which advertisement banner is most clicked by the users, that is, which advertisement banner can give us the maximum reward, we can use various exploration strategies. In this section, let's just use an epsilon-greedy method to find the best advertisement banner.

First, let's import the necessary libraries:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt